The examination of residual plots
Linear and squared residual plots are proposed to assess nonlinearity and heteroscedasticity in regression diagnostics. It is shown that linear residual plots are useful for diagnosing nonlinearity and squared residual plots are powerful for detecting nonconstant variance. A paradigm for the graphical interpretation of residual plots is presented.
Heteroscedasticity, Leverages, Nonlinearity, Outliers
Tsai, Chih-Ling, Zongwu Cai, and Xizhi Wu. "The examination of residual plots." Statistica Sinica 8, no.2 (1998): 445-465.